论文标题
联合建模答案选择的问题 - 答案句子图
Question-Answer Sentence Graph for Joint Modeling Answer Selection
论文作者
论文摘要
这项研究研究了基于图的答案句子选择方法（AS2），这是基于检索的问题答案（QA）系统的重要组成部分。在离线学习期间，我们的模型以无监督的方式构建了每个问题的小规模相关培训图，并与图神经网络集成在一起。图节是回答句子对的问题句子。我们训练和集成了最新模型（SOTA）模型，以计算问题问题，问题 - 答案和答案对之间的分数，并在相关性分数上使用阈值来创建图形边缘。然后进行在线推断以在看不见的查询上解决AS2任务。在两个著名的学术基准和一个现实世界数据集的实验表明，我们的方法始终超过SOTA QA基线模型。
This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems. During offline learning, our model constructs a small-scale relevant training graph per question in an unsupervised manner, and integrates with Graph Neural Networks. Graph nodes are question sentence to answer sentence pairs. We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs, and use thresholding on relevance scores for creating graph edges. Online inference is then performed to solve the AS2 task on unseen queries. Experiments on two well-known academic benchmarks and a real-world dataset show that our approach consistently outperforms SOTA QA baseline models.
